Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Extelligence-ai/bagel --skill authoring-pipelinesgit clone --depth 1 https://github.com/Extelligence-ai/bagelWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/extelligence-ai/bagel/authoring-pipelines)<a href="https://agentmods.dev/skills/extelligence-ai/bagel/authoring-pipelines"><img src="https://agentmods.dev/badge/skills/extelligence-ai/bagel/authoring-pipelines/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/extelligence-ai/bagel/authoring-pipelines"><img src="https://agentmods.dev/badge/skills/extelligence-ai/bagel/authoring-pipelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00281 |
| Opus 5 | $0.00026 | $0.00140 |
| Sonnet 5 | $0.00010 | $0.00056 |
| Haiku 4.5 | $0.00005 | $0.00028 |
Grade A, and why
authoring-pipelines scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Authoring bagel pipelines
The bagel MCP server owns the authoring workflow, including the reduce-vs-snippet decision, window/debounce extraction, and the preview-before-run rule. Do not write pipeline YAML from memory:
- Call
run_poml_capabilitywithpoml_path="./src/agent/compose/pipeline.poml". - Follow it exactly. In particular: always call
preview_pipelineand show the user the summary (events found, data kept) BEFORE running anything. - Use
list_pipeline_capabilitiesfor the exact task/gate module paths and arguments — never guess them. - Execute the approved config through the MCP tools (
run_pipeline, orrun_pipeline_batchfor many sources). The capability also mentions a host CLI (run.py); that path is for users at a terminal in the repo, not for plugin sessions — do not shell out to it.
If the connection fails, the server container is not running — see references/formats.md.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 24 lines · 52 tokens per session scan A 4178ba6ac43c
authoring-pipelines is a skill published in the GitHub repository Extelligence-ai/bagel (397 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 281 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
smarttune-mcp
Read-only SmartTune flight log analysis through MCP tools. 10 tools covering CLI parity (platforms, quality, analyze, pid, fft, magfit, sysid, filter, hardware) plus chart generation. Use for agents that do not have exec/shell/write permission, especially customer-support agents handling .bin/.log/.bbl/.bfl/.ulg…
smarttune
Multi-platform flight log offline analysis and tuning advice. Triggered when user sends .bin/.bbl/.ulg log files for PID/FFT/filter/magnetometer analysis. Supports ArduPilot, Betaflight, and PX4.
mjlab-to-mjswan
Port an mjlab task to mjswan: turn a local or remote GitHub repo that registers mjlab tasks into a browser app. Use when the user wants to run, visualize, or deploy an mjlab task (theirs or a third party's) in the browser with mjswan.
ros2-engineering-skills
ROS 2 engineering: rclcpp/rclpy, colcon/ament, launch, QoS/DDS, tf2/URDF, ros2control, Nav2, MoveIt 2, sensors, runtime provenance, and hardware safety. Use for development, review, debugging, and ROS 1 migration to ROS 2. Not for general C++/Python, unrelated middleware, or web/mobile tasks.
habitat-gs-train
Train and evaluate a navigation policy in the habitat-gs simulator. Covers the full generate-episodes → train → evaluate flow for PointNav / ImageNav / ObjectNav (Habitat-Lab + DDPPO reinforcement learning) and for Vision-and-Language Navigation (StreamVLN, Uni-NaVid). Use when the user wants to train, fine-tune…
perceiving-object-parts
Hierarchical perception for subpart targeting. Detects a parent object first (DINO+VLM), crops the camera image to the parent's bounding box, then detects and segments the named subpart inside the crop (DINO + SAM3), and uncrops + fuses depth to a world-frame OBB/mask/cloud — plus the parent object's OBB and cloud for…